Method of Determining the Next Best Observation Azimuth Using Occlusion Information Based on Depth Image

Abstract

The invention discloses a method for determining a next optimal observation orientation by occlusion information in a depth image, and belongs to the field of computer vision. The method includes the steps: acquiring a depth image of a visual target, occlusion boundaries of the depth image and internal and external parameters of a camera; determining the maximum depth difference adjacent point corresponding to each occlusion boundary point according to occlusion boundary information in the acquired depth image; calculating candidate reference observation directions and observation center points corresponding to small planes on an external surface of an occlusion area by the aid of the occlusion boundary points in the depth image, three-dimensional coordinates of the maximum depth difference adjacent points corresponding to the occlusion boundary points and the current observation orientation of the camera; determining an optimal small plane set of the external surface of the occlusion area based on projection dimension reduction ideology, and calculating the next optimal observation orientation based on information of the optimal small plane set. By the method, priori knowledge of the visual target does not need to be obtained in advance, the observation position of the camera is not defined on a fixing surface, and the method is applicable to the visual targets with different profiles.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a method for determining the next best viewing orientation. Background technique [0002] The determination of the next best observation orientation has always been one of the important and difficult research topics in the fields of 3D reconstruction, robot navigation, automatic assembly, target recognition, etc. It determines the next observation of the camera (sensor) based on the currently observed information. The direction and position from which the maximum amount of unknown information of the scene or visual target can be obtained. [0003] At present, there are two main types of image information based on the next best observation orientation determination algorithm: image brightness information and image depth information. There are relatively few algorithms for determining the next best observation orientation based on image brightness information, and compared with 2D b...

AI Technical Summary

Problems solved by technology

Banta J E and Wong L M in the article "Next-best-view system for autonomous3-D object reconstruction. IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans, 2000, 30(5): 589-598" The observation position determined by the proposed method is limited to a fixed surface (such as the surface of a sphere, the surface of a cylinder, etc.), so the generality of the method is limited.

The method proposed by Chen S Y and Li Y F in the article "Automatic sensor placement for model-based robot vision. IEEETransactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 2004, 34(1): 393-408" needs to be obtained in advance Prior knowledge of the scene, such as the size of visual objects in the scene, etc., so it is not suitable for unknown scenes

Images